Small-data image classification via drop-in variational autoencoder

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F25%3A00636756" target="_blank" >RIV/67985556:_____/25:00636756 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/article/10.1007/s11760-025-04376-1" target="_blank" >https://link.springer.com/article/10.1007/s11760-025-04376-1</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s11760-025-04376-1" target="_blank" >10.1007/s11760-025-04376-1</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Small-data image classification via drop-in variational autoencoder

Popis výsledku v původním jazyce

It is unclear whether generative approaches can achieve state-of-the-art performance with supervised classification in highdimensional feature spaces and extremely small datasets. In this paper, we propose a drop-in variational autoencoder (VAE) for the task of supervised learning using an extremely small train set (i.e., n = 1,..,5 images per class). Drop-in classifiers form a usual alternative when traditional approaches to Few-Shot Learning cannot be used. The classification will be defined as a posterior probability density function and approximated by the variational principle. We perform experiments on a large variety of deep feature representations extracted from different layers of popular convolutional neural network (CNN) architectures. We also benchmark with modern classifiers, including Neural Tangent Kernel (NTK), Support Vector Machine (SVM) with NTK kernel and Neural Network Gaussian Process (NNGP). Results obtained indicate that the drop-in VAE classifier outperforms all the compared classifiers in the extremely small data regime.

Název v anglickém jazyce

Small-data image classification via drop-in variational autoencoder

Popis výsledku anglicky

It is unclear whether generative approaches can achieve state-of-the-art performance with supervised classification in highdimensional feature spaces and extremely small datasets. In this paper, we propose a drop-in variational autoencoder (VAE) for the task of supervised learning using an extremely small train set (i.e., n = 1,..,5 images per class). Drop-in classifiers form a usual alternative when traditional approaches to Few-Shot Learning cannot be used. The classification will be defined as a posterior probability density function and approximated by the variational principle. We perform experiments on a large variety of deep feature representations extracted from different layers of popular convolutional neural network (CNN) architectures. We also benchmark with modern classifiers, including Neural Tangent Kernel (NTK), Support Vector Machine (SVM) with NTK kernel and Neural Network Gaussian Process (NNGP). Results obtained indicate that the drop-in VAE classifier outperforms all the compared classifiers in the extremely small data regime.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Signal Image and Video Processing

ISSN

1863-1703

e-ISSN

1863-1711

Svazek periodika

19

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

CH - Švýcarská konfederace

Počet stran výsledku

9

Strana od-do

766

Kód UT WoS článku

001512352600001

EID výsledku v databázi Scopus

2-s2.0-105008514329